Alternatives and similar repositories for nanoGRPO

Users that are interested in nanoGRPO are comparing it to the libraries listed below

• shangshang-wang / Tina
  Tina: Tiny Reasoning Models via LoRA
  ☆310Updated 3 months ago
• fangyuan-ksgk / Tiny-GRPO
  minimal GRPO implementation from scratch
  ☆100Updated 9 months ago
• open-thought / tiny-grpo
  Minimal hackable GRPO implementation
  ☆306Updated 10 months ago
• Mohammadjafari80 / GSM8K-RLVR
  A simplified implementation for experimenting with RLVR on GSM8K, This repository provides a starting point for exploring reasoning.
  ☆151Updated 10 months ago
• brendanhogan / DeepSeekRL-Extended
  Exploring Applications of GRPO
  ☆250Updated 4 months ago
• ZihanWang314 / CoE
  Chain of Experts (CoE) enables communication between experts within Mixture-of-Experts (MoE) models
  ☆226Updated last month
• rsshyam / GRPO
  ☆68Updated last year
• lucidrains / coconut-pytorch
  Implementation of 🥥 Coconut, Chain of Continuous Thought, in Pytorch
  ☆181Updated 6 months ago
• SalesforceAIResearch / LaTRO
  ☆125Updated 10 months ago
• NVIDIA / ngpt
  Normalized Transformer (nGPT)
  ☆194Updated last year
• sunblaze-ucb / Intuitor
  Code for the paper: "Learning to Reason without External Rewards"
  ☆383Updated 5 months ago
• yihedeng9 / rlhf-summary-notes
  A brief and partial summary of RLHF algorithms.
  ☆139Updated 9 months ago
• vwxyzjn / summarize_from_feedback_details
  ☆160Updated last year
• facebookresearch / memory
  Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, spars…
  ☆362Updated last year
• convergence-ai / lm2
  Official repo of paper LM2
  ☆46Updated 10 months ago
• CMU-AIRe / MRT
  Research Code for preprint "Optimizing Test-Time Compute via Meta Reinforcement Finetuning".
  ☆114Updated 4 months ago
• tokenbender / avataRL
  rl from zero pretrain, can it be done? yes.
  ☆282Updated 3 months ago
• TIGER-AI-Lab / CritiqueFineTuning
  Code for "Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate" [COLM 2025]
  ☆180Updated 5 months ago
• knoveleng / open-rs
  Official repo for paper: "Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't"
  ☆270Updated 2 months ago
• facebookresearch / RAM
  A framework to study AI models in Reasoning, Alignment, and use of Memory (RAM).
  ☆333Updated last week
• SiliangZeng / Multi-Turn-RL-Agent
  ☆99Updated 6 months ago
• jwhj / OREO
  ☆116Updated 11 months ago
• jxiw / MambaInLlama
  [NeurIPS 2024] Official Repository of The Mamba in the Llama: Distilling and Accelerating Hybrid Models
  ☆232Updated 2 months ago
• ServiceNow / PipelineRL
  A scalable asynchronous reinforcement learning implementation with in-flight weight updates.
  ☆340Updated this week
• sail-sg / VeriFree
  Reinforcing General Reasoning without Verifiers
  ☆93Updated 6 months ago
• THU-KEG / Agentic-Reward-Modeling
  [ACL 2025] Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems
  ☆115Updated 6 months ago
• casper-hansen / OpenCoconut
  OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.
  ☆174Updated 11 months ago
• ScalingIntelligence / large_language_monkeys
  ☆111Updated last year
• sail-sg / oat
  🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.
  ☆584Updated this week
• axon-rl / gem
  A Gym for Agentic LLMs
  ☆409Updated this week